© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33772
    Prev
    Next
    INDEX
    Explanations

    matter what, matter how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÐĦ
    -0.11
    ikat
    -0.10
    vale
    -0.10
     sadd
    -0.09
    sed
    -0.09
    Äįe
    -0.08
    sav
    -0.08
    .asp
    -0.08
    -ÑĤо
    -0.08
     âĸ¼
    -0.08
    POSITIVE LOGITS
     what
    0.21
     how
    0.20
    what
    0.17
    how
    0.14
    ä»Ģä¹Ī
    0.12
     whether
    0.12
     where
    0.11
    aub
    0.10
    theless
    0.10
     What
    0.10
    Activations Density 0.009%

    No Known Activations